mcpwatch

← All servers

Grade B

KARTA — spend control for AI agents

lat.rta.karta/guard · v0.1.0 · score 89/100 · checked 2026-11-22

Automated, read-only signal from public data, not an audit or an accusation. Maintainers can dispute any finding. How grading works

Task envelope, budget ledger, kill switch and signed receipts for agents that pay.

Source: https://github.com/mrpkk/onchain-ai-agent

Findings

SeverityRuleDetail
LowMW005Remote endpoint lists 6 tool(s) to anyone, no credentials needed.
MediumMW1021 tool(s) can execute commands or delete data (kill_envelope). Require confirmation before the agent calls them.

What was checked

Public tools: check_spend, open_envelope, get_envelope, kill_envelope, envelope_evidence, policy_rules

Maintainer? Add the badge

Grades refresh daily. Think a finding is wrong? Dispute this grade.

[![mcpwatch](https://www.mcpwatch.io/badge/lat-rta-karta-guard-e5c61d0d.svg)](https://www.mcpwatch.io/s/lat-rta-karta-guard-e5c61d0d)